INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, PROGRAM, AND VEHICLE CONTROL SYSTEM

To estimate the position of a target, for example, with high accuracy.SOLUTION: An information processing device in an embodiment includes an acquisition unit, a detection unit, and an estimation unit. The acquisition unit obtains a plurality of pieces of detection information. The detection informa...

Full description

Saved in:
Bibliographic Details
Main Authors SEKI AKIHITO, SUGIURA TAKAYUKI
Format Patent
LanguageEnglish
Japanese
Published 10.02.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:To estimate the position of a target, for example, with high accuracy.SOLUTION: An information processing device in an embodiment includes an acquisition unit, a detection unit, and an estimation unit. The acquisition unit obtains a plurality of pieces of detection information. The detection information includes a detection result for each two-dimensional position, which is obtained by detecting a target by using electromagnetic waves at a mutually different detection position by one or more detection devices, and includes distortion due to a transmission body that exists between the detection devices and the target and transmits electromagnetic waves. The detection unit detects a feature point from each of the plurality of pieces of detection information. The estimation unit minimizes an error between a detection position of the feature point corrected based on a distortion map indicating distortion for each two-dimensional position and a three-dimensional position corresponding to the feature point, thereby estimating the distortion map, the three-dimensional position, and the detection position.SELECTED DRAWING: Figure 3 【課題】対象の位置などを高精度に推定する。【解決手段】実施形態の情報処理装置は、取得部と、検出部と、推定部と、を備える。取得部は、1以上の検知装置により相互に異なる検知位置で電磁波を用いて対象を検知して得られる、2次元の位置ごとの検知結果を含む情報であって、検知装置と対象との間に存在し、電磁波を透過する透過体による歪みを含む複数の検知情報を取得する。検出部は、複数の検知情報それぞれから特徴点を検出する。推定部は、2次元の位置ごとの歪みを表す歪みマップに基づいて補正した特徴点の検出位置と、特徴点に対応する3次元位置と、の誤差を最小化することにより、歪みマップと、3次元位置と、検知位置と、を推定する。【選択図】図3
Bibliography:Application Number: JP20200129662